203 Lotus blogs updated hourly. Who will post next? Home | Blogs | Search | About 
 
Latest 7 Posts
Watson Conversation How-Tos have been published
Tue, Nov 21st 2017 104
Building Facebook Messenger Bots with Botkit and Watson
Thu, Nov 16th 2017 39
Creating Alexa Skills with OpenWhisk and IBM Watson
Thu, Nov 16th 2017 37
Integrating Applications without writing Code
Tue, Nov 14th 2017 18
Pictures from W-JAX 2017
Fri, Nov 10th 2017 9
Using regular Expressions for Entities in Conversations
Fri, Nov 3rd 2017 7
My Favorite IBM Developer Journeys
Wed, Oct 18th 2017 3
Top 10
Watson Conversation How-Tos have been published
Tue, Nov 21st 2017 104
Building Facebook Messenger Bots with Botkit and Watson
Thu, Nov 16th 2017 39
Creating Alexa Skills with OpenWhisk and IBM Watson
Thu, Nov 16th 2017 37
Deploying Angular 2 Apps to Bluemix
Tue, Apr 11th 2017 26
Integrating Applications without writing Code
Tue, Nov 14th 2017 18
New Slots Filling Functionality in Watson Conversation
Fri, Jun 23rd 2017 12
How to build Facebook Chatbots with IBM Watson
Thu, May 12th 2016 11
Building Slack Bots with IBM Watson Conversation
Mon, Jun 26th 2017 10
Sample of the Watson Retrieve and Rank Service
Tue, Jan 12th 2016 9
Getting started with Tensorflow on IBM Bluemix
Mon, Apr 3rd 2017 9


Introducing the Conversation Optimizer for IBM Watson
Twitter Google+ Facebook LinkedIn Addthis Email Gmail Flipboard Reddit Tumblr WhatsApp StumbleUpon Yammer Evernote Delicious
Niklas Heidloff    

In order to develop conversational experiences it’s important to understand how users are actually using bots. Based on this data conversational experiences can continuously be improved.

Watson Conversation comes with an improve component which helps analyzing and improving bots. Dependent on the service plan all conversations from the last 7, 30 or 90 days are stored. Via the Watson Conversation web interface you can get an overview of the interactions between users and bots, for example the traffic at a specific date. You can also improve how Watson understands user inputs by adding or changing intents and entities. Additionally there is a new recommendations feature which I want to blog about soon.

Watson Conversation provides an API to read the logs. Ansgar Schmidt and I have used this API to built a new tool that helps optimizing conversational experiences. The tool reads conversations of a workspace and provides different filters to find conversation flows that have potential issues and might require improvements.

The Conversation Optimizer for IBM Watson is available as open source. You can install it by clicking the Deploy button or you can run an online demo version. In order to add conversations to the demo version you can use the Conversation Inspector which has been configured to go against the same workspace.

Here is a screenshot showing a list of conversations with potential issues using the sample car dashboard workspace.

all

At this point four filters are provided.

1. Out of Scope

Sample Conversation
Watson: Hi. It looks like a nice drive today. What would you like me to do?
User: Who is Niklas?
Watson: I’m not sure about that. You can say things like “Turn on my lights” or “Play some music.”

In order for this filter to work the dialog needs to be changed by adding ‘”output.outOfScope” : ““‘ to the nodes when the user input is out of scope. These are typically the nodes with the ‘anything_else’ condition.

2. Unfulfilled Intents

Sample Conversation
Watson: Hi. It looks like a nice drive today. What would you like me to do?
User: turn on music
Watson: Sure thing! Which genre would you prefer? Jazz is my personal favorite.
User: Neue Deutsche Welle
Watson: Sorry I don’t recognize that genre. Want to try something? Jazz? Rock?

This filter also requires changes to the dialog definition. Developers can mark intents as being fulfilled when certain nodes in the dialogs are reached. This way intents that have been triggered but not fulfilled can be detected. For this feature to work you need to add information to the JSON of your dialog nodes:
– Add ‘”output.intentTriggered” : “your-intent-name”‘ to the node when the intent is triggered
– Add ‘”output.intentFulfilled” : “your-intent-name”‘ to the node when the intent is fulfilled

3. Unconfident Intents

Sample Conversation
Watson: Hi. It looks like a nice drive today. What would you like me to do?
User: make it warmer
Watson: I understand you want me to turn up something. You can say increase the volume or turn up the AC.

This filter shows all conversations with intents that have less than 50% confidence.

4. Dialog Errors

This filter shows conversations with log messages which indicate errors in the dialog definition.

We’d be happy to get your feedback !

The post Introducing the Conversation Optimizer for IBM Watson appeared first on Niklas Heidloff.



---------------------
http://heidloff.net/article/conversation-optimizer-ibm-watson
Aug 29, 2017
5 hits



Recent Blog Posts
104
Watson Conversation How-Tos have been published
Tue, Nov 21st 2017 8:22a   Niklas Heidloff
I’ve written two How-Tos which describe how to use the Watson Conversation tools Ansgar Schmidt and I had open sourced. The new page on developer.ibm.com contains How-Tos which describe everything that might be of interest for developers using the IBM Cloud. In contrast to patterns How-Tos are typically shorter and sometimes contain ‘only’ documentation and no source code. Inspecting Watson Conversations REST Requests “This how-to explains how to set up and use the commu
39
Building Facebook Messenger Bots with Botkit and Watson
Thu, Nov 16th 2017 10:54a   Niklas Heidloff
I’ve implemented a sample Facebook Messenger bot which leverages the Node.js library Botkit and IBM Watson Conversation. With Botkit you can build bots for Slack, Facebook Messenger, Twilio and other messaging clients. For natural language understanding different services can be used, for example IBM Watson, Api.ai, Wit.ai or Rasa. Most of the code can be shared for Slack and Facebook Messenger bots. Check out the code on GitHub. Similarly to my sample Slack bot, the Facebook Messenger bo
37
Creating Alexa Skills with OpenWhisk and IBM Watson
Thu, Nov 16th 2017 8:43a   Niklas Heidloff
My first code pattern (formerly known as developer journeys) has been published on developer.ibm.com/code. The pattern describes how to build Alexa skills with OpenWhisk. Rather than using intent and entity identification from Alexa, Watson Conversation is used. This allows developers to define conversation flows declaratively and developers can reuse conversations that are available in the Bot Asset Exchange. My colleague Mark Sturdevant improved the documentation and created a video. Check out
18
Integrating Applications without writing Code
Tue, Nov 14th 2017 2:52p   Niklas Heidloff
IBM App Connect is an IPaaS (Integration Platform as a Service) to connect different applications without having to write code. Similarly to IFTTT users are typically business users or citizen developers from line of business departments. App Connect provides currently roughly 50 connectors to integrate applications like Salesforce, SAP, Slack and Gmail. See the documentation for details. Users can graphically build flows that are either event-triggered, for example if a document is changed in a
9
Pictures from W-JAX 2017
Fri, Nov 10th 2017 10:32a   Niklas Heidloff
This week I attended W-JAX in Munich, Germany, which is a developer conference with 1400 attendees with a focus on Java and enterprise technologies. My colleagues and I presented and demonstrated the IBM Cloud and the IBM Code developer site. Below are some pictures. The IBM team: Discussions with developers at the booth: I gave a session about Slack bots and IBM Watson Conversation: One thing I really liked was a demo another company gave at their booth. They connected Anki Overdrive cars to
7
Using regular Expressions for Entities in Conversations
Fri, Nov 3rd 2017 8:06a   Niklas Heidloff
In conversational experiences entities are used to identify classes of objects in user phrases, for example ‘city’ or ‘person’. Watson Conversation supports entity definitions with predefined lists of potential values and synonyms. Recently a new capability has been added so that you can also use regular expressions to identify entities (beta). This functionality is useful when, for example, you want to identify email addresses, phone numbers or URLs without predefining a
3
My Favorite IBM Developer Journeys
Wed, Oct 18th 2017 3:12p   Niklas Heidloff
The team of developer advocates within IBM has created a new site with journeys for developers. Journeys are sample scenarios that are available as open source, well documented and easy to reuse and deploy. There are roughly 60 journeys right now and new ones are published regularly. Check out the journeys at developer.ibm.com/code/journey. Here are my favorite journeys: Make Java microservices resilient with Istio “Twelve-factor apps make a strong case for designing and implementing you
8
Fast On-Ramp for building Cloud-Native Apps
Tue, Oct 17th 2017 9:32a   Niklas Heidloff
In order for developers to get started quickly to build applications and deploy them on the IBM Cloud, new starter kits have been made available. Check out the new IBM Cloud App Service. You can choose from several template the type of application or microservice you want to build: Express.js Backend, Express.js React, Java MicroProfile, Java Spring Backend, Swift Kitura, Python Microservice and more. Additionally you can create new or select existing IBM Cloud services, for example the Watson s
3
How to write your own Slack Chatbots in Javascript
Mon, Oct 16th 2017 2:54p   Niklas Heidloff
Last week Ansgar Schmidt and I gave a session at Codemotion How to write your own Slack Chatbots in Javascript. Below are the slides with screenshots of our demos. We demonstrated how to write a Node.js application that uses Botkit to connect with Slack and that uses IBM Watson Conversation as natural language processing service. Get the code of our sample from GitHub. The post How to write your own Slack Chatbots in Javascript appeared first on Niklas Heidloff.
4
Composing Serverless Apps with IBM Cloud Functions
Tue, Oct 10th 2017 8:13p   Niklas Heidloff
Today at Serverlessconf IBM announced a new key capability (as IBM Research preview) of IBM Cloud Functions. With the new tool ‘Composer‘ apps can be created which contain multiple cloud functions. These apps coordinate the invocations of actions and the data flow. Compared to the previously available action sequences the new functionality is much more flexible. Cloud functions are typically rather simple and focussed on specific tasks which is why people often refer to cloud functio




Created and Maintained by Yancy Lent - About - Planet Lotus Blog - Advertising - Mobile Edition